Server profile

Google Search Console MCP Server

This server connects MCP assistants to Google Search Console data and management actions. SEOs can investigate search performance, inspect indexing, compare periods, and work with sitemaps.

Server facts

Google Search Console MCP Server

Project

Author
AminForou
License
MIT

Tech

Runtime / language
pythonPython
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
1,950
Last commit
Data as of

Tags

  • Google Search Console
  • Indexing
  • Python
  • Search Analytics
  • Seo

Overview

Google Search Console MCP Server brings site performance and indexing data into conversations with an AI assistant. Its tools cover properties, search analytics, URL inspection, and sitemap management. Analysts can inspect clicks, impressions, click-through rate, and position, compare date ranges, or filter results by country, device, query, and page. Page-specific query reports help connect search terms with landing pages. URL tools expose crawl and indexing details, including batch inspection of up to ten URLs per call. A capabilities tool reports the available operations and authentication status.

The README recommends launching the mcp-search-console package through uvx, which handles the Python runtime. Source-checkout installation instead requires Python 3.11 or newer. Authentication can use a downloaded desktop OAuth client configuration, with browser login on first use, or a service-account key whose email has been granted access to the Search Console property. Examples cover desktop and command-line MCP clients, and recommend an absolute uvx path for GUI hosts. Potentially destructive site and sitemap operations are disabled unless explicitly enabled. A data-state setting selects dashboard-like data or finalized results, with the latter carrying a reporting lag. The README promotes a separate hosted offering with additional GA4 tools, but those should not be assumed to belong to this local server. Its primary scope is authenticated access to the user's Search Console properties.

Install & configure

Requirements

  • uv / uvx
  • Google project with Search Console API enabled
  • OAuth desktop client credentials or a service-account key
  • Access to the relevant Search Console property
Documented launch / install command
/FULL/PATH/TO/uvx mcp-search-console

Replace /FULL/PATH/TO/uvx with the actual executable path. This example uses OAuth and opens a browser on first use. Service-account setup instead uses GSC_CREDENTIALS_PATH and GSC_SKIP_OAUTH. The source-install path needs Python 3.11+.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "mcp-gsc": {
      "command": "/FULL/PATH/TO/uvx",
      "args": [
        "mcp-search-console"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "<Absolute path to downloaded desktop OAuth client JSON>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "mcp-gsc": {
      "command": "/FULL/PATH/TO/uvx",
      "args": [
        "mcp-search-console"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "<Absolute path to downloaded desktop OAuth client JSON>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcp-gsc": {
      "type": "stdio",
      "command": "/FULL/PATH/TO/uvx",
      "args": [
        "mcp-search-console"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "<Absolute path to downloaded desktop OAuth client JSON>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "mcp-gsc": {
      "command": "/FULL/PATH/TO/uvx",
      "args": [
        "mcp-search-console"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "<Absolute path to downloaded desktop OAuth client JSON>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcp-gsc": {
      "type": "stdio",
      "command": "/FULL/PATH/TO/uvx",
      "args": [
        "mcp-search-console"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "<Absolute path to downloaded desktop OAuth client JSON>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
get_capabilitiesList available tools and report authentication status.
list_propertiesList the Search Console properties available to the account.
get_site_detailsRetrieve information about a selected property.
get_search_analyticsReport query and page metrics for a selected date range.
get_performance_overviewSummarize property performance over a time period.
compare_search_periodsCompare metrics between two date ranges.
get_search_by_page_queryFind queries contributing traffic to a particular page.
get_advanced_search_analyticsFilter analytics by country, device, query, or page.
inspect_url_enhancedInspect detailed indexing and crawl status for a URL.
batch_url_inspectionInspect up to ten URLs in one request.
check_indexing_issuesCheck several URLs for indexing problems.
get_sitemapsList sitemaps for a property.
list_sitemaps_enhancedRetrieve sitemap details including errors and warnings.
manage_sitemapsSubmit or delete a sitemap, subject to configuration.
reauthenticateRestart browser OAuth login to authenticate again or switch accounts.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Compare search traffic between reporting periods.
  • Find queries driving visits to a specific page.
  • Inspect crawl and indexing problems across URLs.
  • Review sitemap errors and submit sitemaps.
  • Filter performance by device or country.

Strengths

  • Combines search reporting, URL inspection, and sitemap workflows.
  • Supports OAuth and service-account authentication.
  • Destructive operations require explicit enablement.

Limitations

  • Requires Google API credential setup and property access.
  • Batch URL inspection is limited to ten URLs per call.
  • Finalized data has a documented reporting lag.

Frequently asked questions

Yes. The service-account method uses a JSON key, GSC_CREDENTIALS_PATH, and GSC_SKIP_OAUTH, with property access granted to that account.

Call get_capabilities to inspect available tools and current authentication status.

No. GSC_ALLOW_DESTRUCTIVE defaults to false and must be enabled for the listed destructive operations.

The README attributes added GA4 tools to a separate hosted offering, not this local server.

GUI clients may not inherit the shell path, so the README recommends the full executable path.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Excel MCP Server

Data & Analytics

Excel MCP Server lets AI agents create and modify workbooks without an installed copy of Microsoft Excel. It covers worksheet management, formulas, formatting, charts, and pivot tables through local or remote MCP connections.

MCP Server Chart

Data & Analytics

Generate charts, diagrams, maps, and tabular views from an AI assistant using AntV. The TypeScript MCP server supports desktop clients, network transports, and an optional private rendering service.

Grafana MCP Server

Data & Analytics

Connect MCP assistants to Grafana dashboards, datasources, alerts, and incident workflows. It serves observability teams that want to investigate metrics, logs, and traces and manage Grafana resources from an assistant.

MCP Google Sheets

Data & Analytics

MCP Google Sheets lets AI clients work with spreadsheets through Google Sheets and Drive APIs. It supports reading, writing, tab management, sharing, and batch operations, with tool filtering to reduce context usage.

Jupyter MCP Server

Data & Analytics

Jupyter MCP Server lets AI assistants inspect, edit, and execute notebooks with live output feedback. It supports multiple notebooks, multimodal results, JupyterLab commands, and optional execution tracing.

dbt MCP Server

Data & Analytics

dbt MCP Server gives agents project context and operations across dbt Core, Fusion, and Platform. It covers SQL, metrics, lineage, model health, CLI commands, job management, and documentation retrieval.